Nemotron 3 Super
NVIDIAReleased Mar 11, 2026Open weights · NVIDIA Open Model Licensenemotron-3-super-120b-a12b
- Reasoning
- yes, with effort levels
- Knowledge cutoff
- June 2024
- Context
- 262K tokens
- Max output
- 16k tokens
- Input
- text
- API features
- tools, structured outputs, JSON mode, seed, logprobs
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from NVIDIA · cutoff: aiknowledgecutoff.com
Free right now
- Free OpenRouter, served by Nvidia · no end date · 20 req/min, 50 req/day, 1,000 req/day with $10 of credits
Checked Oct 23 · every free model on Deals
Speed by provider
Output speed of Nemotron 3 Super at each host, fastest first
- Crusoe121 tok/s0.42 s to first token
- DeepInfra64 tok/s0.46 s to first token
- DekaLLM32 tok/s1.25 s to first token
Speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · a snapshot of real traffic before the daily read, not a daily average · bars from zero.
Run it yourself
open weights, NVIDIA Open Model License · fits 4 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 120B
- 12B active per token (MoE)
- Memory needed
- 72 GB
- in INT4 · 144 GB in INT8
- Smallest cloud setup
- A100
- 80 GB · $1.19/h, about $869 a month
- Worth it above
- 2B tokens
- a month, against the cheapest API at $0.48 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 72 GB | A100 · $1.19/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 144 GB | 2× H100 · $4.30/h | near-lossless |
| FP16 (full) | 288 GB | 4× H100 · $8.60/h | reference quality |
At home: in INT4 it fits a Mac Studio M5 Ultra (96 GB unified), about $5,499 once, or $0.2092/h over 3 years, electricity aside; it pays for itself after about 11B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| DigitalOcean | $0.30 | $0.65 | $0.06 | — | — | — | Sep 8 |
| Crusoefp8 (bf16) · 256K ctx | $0.30 | $2.40 | $0.15 | 121 | 0.42 s | 100% | Oct 23 |
| DeepInfrabf16 · 256K ctx · 16K out | $0.085 | $0.40 | — | 64 | 0.46 s | 100% | Oct 23 |
| DekaLLMfp8 (bf16) · 256K ctx | $0.08 | $0.45 | — | 32 | 1.25 s | 100% | Oct 23 |
4 of 4 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| DeepInfra | bf16 | 256K | 16K | yes | no | yes |
| DekaLLM | fp8 | 256K | not checked yet | yes | yes | yes |
| DigitalOcean | not checked yet | not checked yet | not checked yet | — | — | — |
| Crusoe | fp8 | 256K | not checked yet | yes | yes | yes |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Nemotron 3 Super spec sheet, field by field, with sources
Nemotron 3 Super spec sheetmaker-declared
What NVIDIA declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 262,144 tokens
- Parameters
- 123,611,012,096≈ 123.6B
- Active experts
- 22 of 512 active per token
- Weight precision
- BF16
- License
- NVIDIA Open Model License — open weights, conditionalcuratedScope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the maker≈ June 2024 third-party estimate — not the maker's figurecurated
- Modalities
- text
- Max output (official)
- to verify
- Release date
- to verify≈ March 11, 2026 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
Also declared in the weights
- Architecture class
- NemotronHForCausalLM
- Layers
- 88
- Vocabulary
- 131,072 tokens
- Weights first published
- March 10, 2026
- Weights last updated
- August 25, 2026
- Languages declared
- English · French · Spanish · Italian · German · Japanese · Chinese
- Papers
- arXiv:2512.20848 · arXiv:2512.20856
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 · config.json @ 2dc98e2 · read 2026-10-08 · 6 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| DeepInfra | $0.28 | $0.88 | $0.74 |
| DekaLLM | $0.30 | $0.86 | $0.77 |
| DigitalOcean | $0.62 | $2.73 | $1.85 |
| Crusoe | $1.50 | $3.60 | $3.60 |
What each host bills for 1,000 requests of a representative job
Your own workload
Also serving Nemotron 3 Super, without a published price
No price we can verify, so no rank.
Other NVIDIA models · all its models, hosts and history ›
- Nemotron 3.5 Super VL7 providers · from $0.50
- Nemotron 3 Nano 30B A3B4 providers · from $0.25
- Nemotron 3.5 Lightning4 providers · from $0.18
- Nemotron 3 Ultra3 providers · from $2.70
- Nemotron 3.5 Content Safety1 provider · from $0.40
- Nemotron 3 Nano Omni 30B A3B Reasoning0 provider · from —